Matthias Hadlich

Confirmed on KDE neon 5.17 which is based on Ubuntu 18.04

The same problem can occur if your GOROOT is wrong which was my problem. Executing the command mentioned above will expose the problem so you then can fix it: `go...

@grlee77 Thanks a lot! I just tried it on the DeepEdit Code and it appears to be 100% compatible to what scipy does, really awesome. For everyone else trying this...

Also for anyone wondering what the impact of this would be, I did some profiling on a full 3D volume. Here is the according snippet: https://gist.github.com/matt3o/0de8a24a10135ed24de6f77ab89e15b1 And the results were:...

As of https://github.com/Project-MONAI/MONAI/pull/6981, the Euclidean distance transform will be part of MONAI from version 1.3 ongoing. It has GPU support via cuCIM and runs a lot faster. Falls back to...

Update: I just saw this is the Linux only repo, I ran into this error on my Windows, I think it applies to Linux as well. Just remove the Windows...

Hey @KumoLiu, thanks for the quick response again! This code is using the DynUNet, however not the default one from monai.networks.nets but a separate file. I just switched to the...

Btw I am not sure if `32**3` is actually allowed by the DynUnet (I have an padding to `64**3` in the code, so I don't think it makes any sense)....

@KumoLiu, then we will have to debug this as soon as I publish my code. I am using exactly the network config you just mentioned. I would guess your problem...

@KumoLiu I get the similar results when using the UNet, but not when I am using the DynUNet. I will append the modified code and the runtime results. I also...